From 6b3a5dc3ce004db60e5932e5a26a1b8fb0cd5891 Mon Sep 17 00:00:00 2001 From: Kerry Lu Date: Fri, 16 Oct 2026 18:04:41 -0700 Subject: [PATCH] docs(cost): rewrite stale completion_cost docstring (#47022) The old docstring called completion_response required, said total_time was in seconds (it is milliseconds), and only covered a handful of the parameters. Replace it with a short accurate summary and fix the "calculat" typo in the unmapped-model error. Co-authored-by: Kerry Lu Co-authored-by: Claude Opus 5.5 --- litellm/cost_calculator.py | 33 ++++++++------------------------- 1 file changed, 8 insertions(+), 25 deletions(-) diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py index d9ee6bdc270..fef6d618e9d 100644 --- a/litellm/cost_calculator.py +++ b/litellm/cost_calculator.py @@ -1438,32 +1438,15 @@ def completion_cost( vertex_location: str | None = None, # for Vertex AI regional-endpoint uplift (e.g. "us-east5", "global") ) -> float: """ - Calculate the cost of a given completion call fot GPT-3.5-turbo, llama2, any litellm supported llm. + Return the USD cost of a LiteLLM call. - Parameters: - completion_response (litellm.ModelResponses): [Required] The response received from a LiteLLM completion request. + Pass `completion_response` to price a response LiteLLM returned. Without one, pass `model` plus + `messages` / `prompt` and `completion`, and token counts are computed from the text. Prices come from + `litellm.model_cost` unless `custom_cost_per_token` or `custom_cost_per_second` is given. `total_time` + is in milliseconds and only matters for per-second pricing such as Replicate and SageMaker. - [OPTIONAL PARAMS] - model (str): Optional. The name of the language model used in the completion calls - prompt (str): Optional. The input prompt passed to the llm - completion (str): Optional. The output completion text from the llm - total_time (float, int): Optional. (Only used for Replicate LLMs) The total time used for the request in seconds - custom_cost_per_token: Optional[CostPerToken]: the cost per input + output token for the llm api call. - custom_cost_per_second: Optional[float]: the cost per second for the llm api call. - - Returns: - float: The cost in USD dollars for the completion based on the provided parameters. - - Exceptions: - Raises exception if model not in the litellm model cost map. Register model, via custom pricing or PR - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json - - - Note: - - If completion_response is provided, the function extracts token information and the model name from it. - - If completion_response is not provided, the function calculates token counts based on the model and input text. - - The cost is calculated based on the model, prompt tokens, and completion tokens. - - For certain models containing "togethercomputer" in the name, prices are based on the model size. - - For un-mapped Replicate models, the cost is calculated based on the total time used for the request. + Raises if no candidate model name resolves to pricing. Register the model via `litellm.register_model` + or add it to model_prices_and_context_window.json. """ try: call_type = infer_call_type(call_type, completion_response) or "completion" @@ -2066,7 +2049,7 @@ def completion_cost( ) if idx == len(potential_model_names) - 1: raise e - raise Exception(f"Unable to calculat cost for received potential model names - {potential_model_names}") + raise Exception(f"Unable to calculate cost for received potential model names - {potential_model_names}") except Exception as e: raise e